Cognitive Training Assistant for Cost Estimators
AUTHORS: Dr. Daniel Selva1, Dr. Theodora Chaspari1, Dr. Alejandro Salado2
TEXAS A&M UNIVERSITY 1, UNIVERSITY OF ARIZONA 2
Cognitive assistants (CAs) enable humans to solve complex tasks and problems more efficiently. The goal of this project, led by Principal Investigator (PI) Dr. Daniel Selva (Texas A&M University), was to demonstrate proof of concept for a CA that would assist in training new cost estimators in the Department of Defense (DoD). This CA was developed to provide trainees with interactive, hands-on opportunities to learn concepts, methods, and best practices related to estimating the lifecycle costs of complex systems. The systems can be used to improve student-learning outcomes and engagement by providing them with learning opportunities tailored to their specific needs.
Currently, the training of new cost estimators is done primarily through traditional instruction in live classrooms, and thus it is a time-consuming process. The use of CAs can allow for more interactive and tailored instruction for each individual and area, as demonstrated with intelligent tutoring systems in other areas of education.
The idea of using AI tools to enhance the learning of trainees is not new and has been studied for decades. However, in the DoD Acquisition context, we are still in the early stages of incorporating advanced AI tools into workflows and, in particular, CAs have not yet been adopted as training tools.
Previous attempts to adopt this technology in the workplace failed because of a combination of insufficient performance of the underlying machine learning models and lack of familiarity of the users with this mode of interaction. With CAs now being ubiquitous in our daily lives, and the significant recent advances we have seen in machine learning, the time is now ripe for infusion of this technology in the workplace.